Subrata Kumar Midya
Bio: Subrata Kumar Midya is an academic researcher from University of Calcutta. The author has contributed to research in topics: Ionosphere & Monsoon. The author has an hindex of 4, co-authored 18 publications receiving 51 citations.
TL;DR: In this article, a comparative study among two neurocomputing models in the form of Multilayer Perceptron (MLP) models and non-linear regression for the prediction of surface ozone (O3) during pre-monsoon season over Gangetic West Bengal (GWB), India considering NOx, SO2, PM10 and temperature as predictors.
Abstract: The present paper reports a comparative study among two neurocomputing models in the form of Multilayer Perceptron (MLP) models and non-linear regression for the prediction of surface ozone (O3) during pre-monsoon season over Gangetic West Bengal (GWB), India considering NOx, SO2, PM10 and temperature as predictors. Learning the MLPs through gradient descent (GD) with tanhyperbolic and sigmoid nonlinearities, we found that all the models under consideration have almost the same degrees of prediction efficiency for O3 over GWB during pre-monsoon season with the said predictors. However, the MLP model with tanhyperbolic activation function is found to produce a significantly higher correlation and Willmott's index of agreement between actual and predicted O3 than the other models. Finally, MLP with GD learning characterized by tanhyperbolic nonlinearity is identified to have significant efficiency in surface ozone prediction over the region as mentioned above.
TL;DR: In this paper, the authors proposed a new index, i.e., multivariate phenology-based agricultural drought index (MADI), for quantification of the agricultural drought using long-term (1982-2015) crop phenological parameters.
Abstract: The objective, accurate and rapid quantification of agricultural drought is the key component of effective drought planning and management mechanism. The present study proposed a new index, i.e. multivariate phenology-based agricultural drought index (MADI), for quantification of the agricultural drought using long-term (1982–2015) crop phenological parameters. The 15-day global inventory modelling and mapping studies time-series normalized difference vegetation index (NDVI) data (~ 8 km) were interpolated at daily scale and smoothened using Savitzky and Golay filtering technique. Different crop phenological parameters, i.e. start of season, end of season, length of the growing period (lgp), integrated NDVI (iNDVI), etc., were estimated using a combination of threshold and derivative approaches for individual pixels during kharif season. Based on the time of occurrence, the agricultural droughts may lead to delay in crop sowing, reduction in cropped area and/or decreased production. Hence, the lgp and iNDVI were selected among all phenological parameters for their capability to represent alterations in crop duration and crop production, respectively. The long-term lgp and iNDVI of individual pixel were detrended and transformed into standardized lgp (Slgp) and standardized iNDVI (SiNDVI) to eliminate the existing trends developed due to technological improvements during study period and existing heterogeneity of Indian agricultural system, respectively. The MADI was calculated by fitting Slgp and SiNDVI into joint probability distribution, where the best joint distribution family along with associated parameters was selected based on the goodness-of-fit for individual pixel. The values of MADI vary between − 4 and + 4, where the negative and positive values represent drought and non-drought conditions, respectively. The efficacy of the proposed index was tested over the Indian region by comparing with the multivariate standardized drought index, which considers the impacts of both meteorological and soil moisture drought using copula approach.
TL;DR: In this article, an information theoretic approach based on Shannon entropy is adopted to discern the influence of pre-monsoon thunderstorm on some surface parameters, and artificial neural network in the form of multilayer perceptron with backpropagation learning is attempted to develop predictive model for surface temperature.
Abstract: An information theoretic approach based on Shannon entropy is adopted in this study to discern the influence of pre-monsoon thunderstorm on some surface parameters. A few parameters associated with pre-monsoon thunderstorms over a part of east and northeast India are considered. Maximization of Shannon entropy is employed to test the relative contributions of these parameters in creating this weather phenomenon. It follows as a consequence of this information theoretic approach that surface temperature is the most important parameter among those considered. Finally, artificial neural network in the form of multilayer perceptron with backpropagation learning is attempted to develop predictive model for surface temperature.
TL;DR: In this article, the D-region ionospheric disturbances due to the tropical cyclone Fani over the Indian Ocean have been analyzed using Very Low Frequency (VLF) radio communication signals from three transmitters (VTX, NWC and JJI) received at two low latitude stations (Kolkata-CUB and Cooch Behar-CHB).
Abstract: The D-region ionospheric disturbances due to the tropical cyclone Fani over the Indian Ocean have been analysed using Very Low Frequency (VLF) radio communication signals from three transmitters (VTX, NWC and JJI) received at two low latitude stations (Kolkata-CUB and Cooch Behar-CHB). The cyclone Fani formed from a depression on 26th April, 2019 over the Bay of Bengal (Northeastern part of the Indian Ocean) and turned into an extremely severe cyclone with maximum 1-minute sustained winds of 250 km/h on 2 May, 2019 which made landfall on 3 May, 2019. Out of six propagation paths, five propagation paths, except the JJI-CHB which was far away from the cyclone track, showed strong perturbations beyond 3 σ level compared to unperturbed signals. Consistent good correlations of VLF signal perturbations with the wind speed and cyclone pressure have been seen for both the receiving stations. Computations of radio signal perturbations at CUB and CHB using the Long Wave Propagation Capability (LWPC) code revealed a Gaussian perturbation in the D-region ionosphere. Analysis of atmospheric temperature at different layers from the NASA’s TIMED satellite revealed a cooling effect near the tropopause and warming effects near the stratopause and upper mesosphere regions on 3 May, 2019. This study shows that the cyclone Fani perturbed the whole atmosphere, from troposphere to ionosphere and the VLF waves responded to the disturbances in the conductivity profiles of the lower ionosphere.
TL;DR: In this paper, the authors estimate the likelihood of vegetation droughts across India in changing scenarios of temperature, precipitation and soil moisture content, and study the resilience of vegetation cover to disturbances induced by a dry condition.
Abstract: Vegetation distribution and growth are significantly affected by changing climate conditions. Understanding the response of vegetation to hydroclimatic disturbances such as droughts is crucial in context of climate change. The sensitivity of terrestrial ecosystem to drought is difficult to measure because of problems related to drought quantification, variable response of vegetation types and changing climate-vegetation dynamics. Since, India is hugely dependent on its vegetation and cropland, identifying the impact of droughts on vegetation is essential. In this study, we estimate the likelihood of vegetation droughts across India in changing scenarios of temperature, precipitation and soil moisture content. We also study the resilience of vegetation cover to disturbances induced by a dry condition. From the investigation, it is observed that at least half the area of 16 out of 24 major river basins is facing high chances of vegetation droughts due to lowered soil moisture levels. The croplands are most likely to be affected by drought, which is of paramount concern for country's food security. Further investigation suggests that at least one-third area of 18 river basins is non-resilient to vegetation droughts. Moreover, >50% of each vegetation type is non-resilient, which points out the fragility of country's terrestrial ecosystems. This study facilitates the understanding of vegetation drought hotspot regions, factors risking the terrestrial ecosystem and their ability to withstand such conditions. These findings provide useful insights for policy makers to develop effective strategies for vegetation drought mitigation and sustainable ecosystem management.
TL;DR: The results obtained in the form of methane concentration prediction demonstrated minor errors in relation to the recorded values of this concentration, offering an opportunity for a broader application of intelligent systems for effective prediction of mining hazards.
Abstract: Methane, which is released during mining exploitation, represents a serious threat to this process. This is because the gas may ignite or cause an explosion. Both of these phenomena are extremely dangerous. High levels of methane concentration in mine headings disrupt mining operations and cause the risk of fire or explosion. Therefore, it is necessary to monitor and predict its concentration in the areas of ongoing mining exploitation. The paper presents the results of tests performed to improve work safety. The article presents the methodology of using artificial neural networks for predicting methane concentration values in one mining area. The objective of the paper is to develop an effective method for forecasting methane concentration in the mining industry. The application of neural networks for this purpose represents one of the first attempts in this respect. The method developed makes use of direct methane concentration values measured by a system of sensors located in the exploitation area. The forecasting model was built on the basis of a Multilayer Perceptron (MLP) network. The corresponding calculations were performed using a three-layered network with non-linear activation functions. The results obtained in the form of methane concentration prediction demonstrated minor errors in relation to the recorded values of this concentration. This offers an opportunity for a broader application of intelligent systems for effective prediction of mining hazards.
TL;DR: This paper proposes a big data-driven dynamic estimation model of relief supplies demand, which merges the dynamic population distribution from Baidu big data and Multilayer Perceptron (MLP) neural network so as to improve the accuracy and timeliness.
Abstract: The dynamic relief supplies estimation for urban flood disaster still remains an important and challenging topic in emergency response. Traditional relief supplies estimation mainly depends on static census data rather than dynamic spatio-temporal population distribution, which may easily lead to a serious imbalance between supply and demand for relief resources. The emergence of big data originating from web mapping service, social media, crowdsourcing system and other methods provides alternative data sources to understand the dynamic distribution of urban population, which can help accurately estimating the relief supplies demand when urban flood occurs. This paper proposes a big data-driven dynamic estimation model of relief supplies demand, which merges the dynamic population distribution from Baidu big data and Multilayer Perceptron (MLP) neural network so as to improve the accuracy and timeliness. Taking Wuhan as an example, a specific day in summer flooding period was chosen to dynamically predict three kinds of relief materials. The results indicate that the proposed model is more feasible to estimate the relief supplies because it is integrated with MLP neural network trained by national-wide historical flood disaster cases and Baidu big data. The utility of Baidu big data for flood-affected population statistics has been shown to be more comprehensive than that of the traditional demographic methods. Thorough analysis exhibits the superiority of our proposed model with respect to accuracy and dynamics. This allows our proposed model to be more widely applied in pre- and post-disaster operations activities carried out by government and humanitarian aid organizations.
TL;DR: In this paper, the water storage dynamics and extremes in the basin during 2002-2020 were quantified, for the first time, using GRACE (Follow-On) based terrestrial water storage anomaly (TWSA) with the help of a novel artificial neural network-based model for the data gap filling.
Abstract: A holistic assessment of the hydroclimatic extremes, which have caused tremendous environmental, societal, and economic losses globally, is imperative for the highly vulnerable Chao Phraya River Basin. In this study, the water storage dynamics and extremes in the basin during 2002–2020 were quantified, for the first time, using GRACE (Follow-On) based terrestrial water storage anomaly (TWSA) with the help of a novel artificial neural network-based model for the data gap filling. TWSA showed a linear trend of −1.12 ± 0.05 cm yr−1 (equivalent to a volumetric trend of −1.79 ± 0.08 km3 yr−1) in the basin, and segregation of the constituent components of TWS revealed that the groundwater storage is a significant contributor (45%) to TWS with a linear trend of −0.51 ± 0.06 cm yr−1 (-0.82 ± 0.10 km3 yr−1) followed by surface water storage (i,e., cumulative of the water storage in the reservoirs, flood inundation, and rivers) (36%) and soil moisture storage (19%). The hydroclimatic extremes detected in TWSA are primarily triggered by the variations in precipitation during the monsoon season (May to October) and further amplified by the subsequent water storage and abstraction. TWSA attained a maximum of 42.86 cm in October 2011 during severe floods of 2011 (~95% increase in net precipitation during 2010 and 2011) and a minimum of −31.81 cm during the drought of May 2020 (~82% decrease in net precipitation during 2019 and 2020). All other flood and drought events in some years, e.g., 2006, 2010, 2015, 2016, are also well recorded in TWSA, albeit with a lag time of up to a maximum of two months from precipitation. Further, the basin’s increasing potential of severe drought, as assessed by the effective water-storage-based novel drought potential index (DPI), underscored the need for multifaceted water management essentially focused on the demand side rather than the supply side in the basin. The proposed framework can be utilized for policymaking for adequate and equitable water allocation, developing the early warning systems for the droughts and floods, and employing the optimal adaptation measures in the Chao Phraya River Basin and other data-scarce river basins globally.
TL;DR: In this paper, the authors used the geo-ecological information-modeling system (GIMS) as one of the Big Data tools to address the problem of pollution in the Arctic Basin.
Abstract: One of the most important problems in the Arctic Basin is the pollution of its waters and the assessment of its impact on the ecological system of this region. In this paper, we recommend using the geoecological information-modeling system (GIMS) as one of the Big Data tools to address this problem. Specifically, the GIMS includes a series of specific models describing ecological, hydrological, climatic, and hydrochemical processes in Arctic waters. The synthesis of GIMS with the Arctic Basin Ecosystem (ABE) model provides the GIMS-ABE coupled model that takes into account various sources of pollutants, including river runoffs, long-range atmospheric transport, and anthropogenic activities in the coastal zone, as well as ships. In the simulation experiments performed in the present study, heavy metals, oil hydrocarbons, and radionuclides are considered as primary contaminants. In addition, the biocomplexity and survivability indicators were considered as information values to predict the status of the Arctic ecosystem. The results showed a high sensitivity of the Arctic ecosystem to pollution that is currently close to a tipping point. In particular, it emerged that the current state of pollution intensity leads to increased accumulation of pollutants in marine waters at different rates ranging from 7 to 23% depending on the Arctic aquatic environment.